Prediction of Strength Parameters of Himalayan Rocks: A Statistical and ANFIS Approach

The knowledge of geomechanical properties of rocks is essential for planning and design of structures in civil, mining, and other allied industries. Direct assessment of these properties is quite expensive and time consuming. It also requires fine precision in sample preparation and high-end testing...

Full description

Saved in:
Bibliographic Details
Published in:Geotechnical and geological engineering 2015-10, Vol.33 (5), p.1255-1278
Main Authors: Kainthola, Ashutosh, Singh, P. K., Verma, Dhananjai, Singh, Rajesh, Sarkar, K., Singh, T. N.
Format: Article
Language:English
Subjects:
Adaptive systems
Artificial neural networks
Civil Engineering
Earth and Environmental Science
Earth Sciences
Fuzzy logic
Fuzzy systems
Geomechanics
Geotechnical Engineering & Applied Earth Sciences
Hydrogeology
Industry
Instruments
Internal friction
Original Paper
Parameters
Properties
Regression analysis
Rock
Rock properties
Rocks
Sample preparation
Sediment samples
Statistical analysis
Statistical methods
Statistical prediction
Terrestrial Pollution
Waste Management/Waste Technology
Wave velocity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The knowledge of geomechanical properties of rocks is essential for planning and design of structures in civil, mining, and other allied industries. Direct assessment of these properties is quite expensive and time consuming. It also requires fine precision in sample preparation and high-end testing instruments. To overcome these problems, 597 rock samples of four different Himalayan rock types have been tested for their strength attributes in a laboratory. The test results were correlated with their P-wave velocity using linear regression analysis for estimation of compressive, tensile, cohesive strengths and angle of internal friction. Subsequently, an adaptive neuro-fuzzy inference system (ANFIS) technique was applied to find its efficiency as a predictor against normal regression system. The results indicated that the ANFIS is comparatively better at prediction of geotechnical strength parameters when pitted against regression techniques.
ISSN:0960-3182
1573-1529
DOI:10.1007/s10706-015-9899-z